Search papers, labs, and topics across Lattice.
This paper introduces PogRE, a novel method for knowledge graph embedding that addresses the issue of pattern over-generalization, where embeddings derived from single instances of patterns are inappropriately generalized across all instances. By employing dense linear transformations and compound operations, PogRE ensures that patterns become progressively universal as more triples are observed, thus improving the robustness of relation representations. Experimental evaluations on benchmark datasets reveal that PogRE outperforms existing KGE models in link prediction while effectively mitigating the adverse effects of over-generalization.
Pattern over-generalization in knowledge graph embeddings can be effectively mitigated with PogRE, leading to superior link prediction performance.
Knowledge graph embedding (KGE) demonstrates its effectiveness for predicting missing links in knowledge graphs (KGs) by projecting entities and relations into a low-dimensional vector space. It is crucial for KGE models to effectively capture inference patterns (patterns) inherent in KGs, such as symmetry/antisymmetry, inversion and composition. Although recent KGE models exhibit strong capabilities in modeling such diverse patterns, they suffer from inherent limitations stemming from pattern over-generalization, where embeddings learned from only a single pattern instance inevitably generalize that pattern to all related instances, i.e., generalize the pattern universally. To address this issue, we propose PogRE (Pattern Over-Generalization Robust Embedding), a simple but effective method that utilizes dense linear transformations and compound operations for relation representation. Our theoretical analysis demonstrates that a dense linear transformation allows a pattern to become progressively universal as more triples are observed in the pattern. Furthermore, after observing d+1 linearly independent entities (d+1 denotes the dimension of entity), the linear transformation guarantees universal generalization of the pattern across all related instances. Experimental results on three standard benchmark datasets show that PogRE outperforms existing state-of-the-art KGE models in link prediction. Moreover, our empirical results indicate that PogRE effectively addresses the negative impact of over-generalization.
